Tree segmentation in airborne laser scanning data is only accurate for canopy trees
Tree segmentation in airborne laser scanning data is only accurate for canopy trees
复制标题
DOI：
10.1101/2022.11.29.518407
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Yujie Cao;James G. C. Ball;D. Coomes;Leon Steinmeier;Nikolai Knapp;P. Wilkes;M. Disney;K. Calders;A. Burt;Yi Lin;Tobias Jackson
中科院分区：
文献类型：
--
作者：
Yujie Cao;James G. C. Ball;D. Coomes;Leon Steinmeier;Nikolai Knapp;P. Wilkes;M. Disney;K. Calders;A. Burt;Yi Lin;Tobias Jackson
从机载激光扫描数据中分割树木是森林遥感领域长期存在的重要挑战。有许多分割算法，但由于难以获得可靠的参考数据，因此稳健的比对研究很少。在这里，我们提供了根据标记的陆地激光扫描数据生成的温带和热带阔叶林的基准数据集。我们将四种广泛使用的树分割算法与该基准数据集的性能进行比较。所有算法都对冠层树木实现了合理的准确度，但对林下树木的准确度非常低。基于点云的算法 AMS3D（自适应均值平移 3D）具有最高的整体精度，紧随其后的是基于 2D 栅格的区域生长算法 Dalponte2016+。这一结果在两种森林类型中都是一致的。这项研究强调需要直接使用基准数据评估树分割算法。我们提供了第一个公开可用的热带森林基准数据集，我们希望未来的研究能够将这项工作扩展到其他地区。
Individual tree segmentation from airborne laser scanning data is a longstanding and important challenge in forest remote sensing. There are a number of segmentation algorithms but robust intercomparison studies are rare due to the difficulty of obtaining reliable reference data. Here we provide a benchmark data set for temperate and tropical broadleaf forests generated from labelled terrestrial laser scanning data. We compare the performance of four widely used tree segmentation algorithms against this benchmark data set. All algorithms achieved reasonable accuracy for the canopy trees, but very low accuracy for the understory trees. The point cloud based algorithm AMS3D (Adaptive Mean Shift 3D) had the highest overall accuracy, closely followed by the 2D raster based region growing algorithm Dalponte2016+. This result was consistent across both forest types. This study emphasises the need to assess tree segmentation algorithms directly using benchmark data. We provide the first openly available benchmark data set for tropical forests and we hope future studies will extend this work to other regions.